© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 2489
    Prev
    Next
    INDEX
    Explanations

    information related to events or situations involving governments, policies, legislation, and societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    580
    +0.12
    0.6%
    481
    +0.11
    0.5%
    689
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.12
    0.05
    288
    +0.11
    0.07
    762
    +0.11
    0.07
    Negative Logits
    iven
    -0.62
     Siber
    -0.61
    Disable
    -0.60
    ãĥķãĤ©
    -0.57
    ãĤ»
    -0.56
    Ox
    -0.56
    Written
    -0.55
    Dim
    -0.55
    ãĥij
    -0.54
     Krish
    -0.54
    POSITIVE LOGITS
     tended
    0.95
     ought
    0.88
     deserve
    0.88
     are
    0.87
     aren
    0.81
     were
    0.80
     tend
    0.80
     may
    0.78
     weren
    0.77
     cannot
    0.77
    Activations Density 0.599%

    No Known Activations